metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: BertAbstractComp
results: []
BertAbstractComp
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7130
- Accuracy: 0.8062
- Precision: 0.4972
- Recall: 0.4770
- F1: 0.4772
- Top3: 0.9490
- Top3macro: 0.7051
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Top3 | Top3macro |
|---|---|---|---|---|---|---|---|---|---|
| 0.4172 | 1.0 | 1640 | 0.9578 | 0.7640 | 0.4137 | 0.3973 | 0.3969 | 0.9292 | 0.6189 |
| 0.4051 | 2.0 | 3280 | 0.7427 | 0.8024 | 0.4759 | 0.4656 | 0.4654 | 0.9430 | 0.6759 |
| 0.2359 | 3.0 | 4920 | 0.8947 | 0.8015 | 0.4735 | 0.4777 | 0.4654 | 0.9402 | 0.6772 |
| 0.1543 | 4.0 | 6560 | 0.9402 | 0.8097 | 0.4900 | 0.4890 | 0.4839 | 0.9475 | 0.7062 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.2.1
- Tokenizers 0.19.1